Weilong Liu

About

Weilong Liu is a robotics researcher whose work focuses on the intersection of model-based control and machine learning for legged locomotion. His primary research areas include bipedal robot control, model predictive control (MPC), and deep reinforcement learning (DRL). Liu’s major contribution lies in bridging the gap between classical dynamics and modern learning-based methods. In his highly cited 2022 paper, he innovatively modified the single rigid body (SRB) model to account for the swinging leg as a disturbance to centroidal and rotational acceleration, then proposed a deep reinforcement learning-based MPC framework to robustly resist these perturbations. This work, with 6 citations, demonstrates his ability to integrate physical modeling with data-driven adaptation, offering a practical solution for stable bipedal walking under real-world disturbances. Liu’s research is notable for its clear engineering focus—improving controller robustness without sacrificing computational efficiency—making it valuable for both academic researchers and roboticists developing humanoid or bipedal platforms. His work exemplifies the growing trend of hybrid control architectures that combine the interpretability of model-based methods with the adaptability of reinforcement learning.

Research Focus

Key Achievements

Top Papers

1. 1
   Deep Reinforcement Learning for Model Predictive Controller Based on Disturbed Single Rigid Body Model of Biped Robots

   6 citations · 2022

Key Collaborators

Contact & Links